Search

The generative self-supervised learning strategy exhibits remarkable learning representational capabilities. However, there is limited attention to end-to-end pre-training methods based on a hybrid architecture of CNN and Transformer, which can learn strong local and global representations simultaneously. To address this issue, we propose a generative pre-training strategy called Hybrid Sparse masKing (HySparK) based on masked image modeling and apply it to large-scale pre-training on medical images. First, we perform a bottom-up 3D hybrid masking strategy on the encoder to keep consistency masking. Then we utilize sparse convolution for the top CNNs and encode unmasked patches for the bottom vision Transformers. Second, we employ a simple hierarchical decoder with skip-connections to achieve dense multi-scale feature reconstruction. Third, we implement our pre-training method on a collection of multiple large-scale 3D medical imaging datasets. Extensive experiments indicate that our proposed pre-training strategy demonstrates robust transfer-ability in supervised downstream tasks and sheds light on HySparK's promising prospects. The code is available at https://github.com/FengheTan9/HySparK, Comment: Early accept at MICCAI 2024

The classical stability margin analysis based on the linearized model is widely used in practice even in nonlinear systems. Although linear analysis techniques are relatively standard and have simple implementation structures, they are prone to misbehavior and failure when the system is performing an off-nominal operation. To avoid the drawbacks and exploit the advantages of linear analysis methods and frequency-domain stability margin analysis while tackling system nonlinearity, a state-compensation-linearization-based stability margin analysis method is studied in the paper. Based on the state-compensation-linearization-based stabilizing control, the definition and measurement of the stability margin are given. The l2 gain margin and l2 time-delay margin for the closed-loop nonlinear system with state-compensation-linearization-based stabilizing control are defined and derived approximatively by the small-gain theorem in theory. The stability margin measurement can be carried out by the frequency-sweep method in practice. The proposed method is a data-driven method for obtaining the stability margin of nonlinear systems, which is practical and can be applied to practical systems directly. Finally, three numerical examples are given to illustrate the effectiveness of the proposed method.

The linearization method builds a bridge from mature methods for linear systems to nonlinear systems and has been widely used in various areas. There are currently two main linearization methods: Jacobian linearization and feedback linearization. However, the Jacobian linearization method has approximate and local properties, and the feedback linearization method has a singularity problem and loses the physical meaning of the obtained states. Thus, as a kind of complementation, a new linearization method named state compensation linearization is proposed in the paper. Their differences, advantages, and disadvantages are discussed in detail. Based on the state compensation linearization, a state-compensation-linearization-based control framework is proposed for a class of nonlinear systems. Under the new framework, the original problem can be simplified. The framework also allows different control methods, especially those only applicable to linear systems, to be incorporated. Three illustrative examples are also given to show the process and effectiveness of the proposed linearization method and control framework.

Recently, the concept of optimal virtual tube has emerged as a novel solution to the challenging task of navigating obstacle-dense environments for swarm robotics, offering a wide ranging of applications. However, it lacks an efficient homotopic path planning method in obstacle-dense environments. This paper introduces Tube-RRT*, an innovative homotopic path planning method that builds upon and improves the Rapidly-exploring Random Tree (RRT) algorithm. Tube-RRT* is specifically designed to generate homotopic paths for the trajectories in the virtual tube, strategically considering opening volume and tube length to mitigate swarm congestion and ensure agile navigation. Through comprehensive comparative simulations conducted within complex, large-scale obstacle environments, we demonstrate the effectiveness of Tube-RRT*., Comment: 8 pages, 8 figures, submitted to RA-L

In recent years, reports of illegal drones threatening public safety have increased. For the invasion of fully autonomous drones, traditional methods such as radio frequency interference and GPS shielding may fail. This paper proposes a scheme that uses an autonomous multicopter with a strapdown camera to intercept a maneuvering intruder UAV. The interceptor multicopter can autonomously detect and intercept intruders moving at high speed in the air. The strapdown camera avoids the complex mechanical structure of the electro-optical pod, making the interceptor multicopter compact. However, the coupling of the camera and multicopter motion makes interception tasks difficult. To solve this problem, an Image-Based Visual Servoing (IBVS) controller is proposed to make the interception fast and accurate. Then, in response to the time delay of sensor imaging and image processing relative to attitude changes in high-speed scenarios, a Delayed Kalman Filter (DKF) observer is generalized to predict the current image position and increase the update frequency. Finally, Hardware-in-the-Loop (HITL) simulations and outdoor flight experiments verify that this method has a high interception accuracy and success rate. In the flight experiments, a high-speed interception is achieved with a terminal speed of 20 m/s.

Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of foundation models in medical image analysis, it is hard to train fair models from scratch while preserving utility. In this paper, we propose a novel method, Adversarial Privacy-aware Perturbations on Latent Embedding (APPLE), that can improve the fairness of deployed segmentors by introducing a small latent feature perturber without updating the weights of the original model. By adding perturbation to the latent vector, APPLE decorates the latent vector of segmentors such that no fairness-related features can be passed to the decoder of the segmentors while preserving the architecture and parameters of the segmentor. Experiments on two segmentation datasets and five segmentors (three U-Net-like and two SAM-like) illustrate the effectiveness of our proposed method compared to several unfairness mitigation methods.

With the rapid expansion of machine learning and deep learning (DL), researchers are increasingly employing learning-based algorithms to alleviate diagnostic challenges across diverse medical tasks and applications. While advancements in diagnostic precision are notable, some researchers have identified a concerning trend: their models exhibit biased performance across subgroups characterized by different sensitive attributes. This bias not only infringes upon the rights of patients but also has the potential to lead to life-altering consequences. In this paper, we inspect a series of DL segmentation models using two ultrasound datasets, aiming to assess the presence of model unfairness in these specific tasks. Our findings reveal that even state-of-the-art DL algorithms demonstrate unfair behavior in ultrasound segmentation tasks. These results serve as a crucial warning, underscoring the necessity for careful model evaluation before their deployment in real-world scenarios. Such assessments are imperative to ensure ethical considerations and mitigate the risk of adverse impacts on patient outcomes., Comment: Submitted to ISBI 2024

Due to the scarcity and specific imaging characteristics in medical images, light-weighting Vision Transformers (ViTs) for efficient medical image segmentation is a significant challenge, and current studies have not yet paid attention to this issue. This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level. In order to leverage the inductive bias inherent in CNNs, we abstract a Transformer-like lightweight CNNs block (ConvUtr) as the patch embeddings of ViTs, feeding Transformer with denoised, non-redundant and highly condensed semantic information. Moreover, an adaptive Local-Global-Local (LGL) block is introduced to facilitate efficient local-to-global information flow exchange, maximizing Transformer's global context information extraction capabilities. Finally, we build an efficient medical image segmentation model (MobileUtr) based on CNN and Transformer. Extensive experiments on five public medical image datasets with three different modalities demonstrate the superiority of MobileUtr over the state-of-the-art methods, while boasting lighter weights and lower computational cost. Code is available at https://github.com/FengheTan9/MobileUtr., Comment: 13 pages

This paper presents an open-source dataset RflyMAD, a Multicopter Abnomal Dataset developed by Reliable Flight Control (Rfly) Group aiming to promote the development of research fields like fault detection and isolation (FDI) or health assessment (HA). The entire 114 GB dataset includes 11 types of faults under 6 flight statuses which are adapted from ADS-33 file to cover more occasions in which the multicopters have different mobility levels when faults occur. In the total 5629 flight cases, the fault time is up to 3283 minutes, and there are 2566 cases for software-in-the-loop (SIL) simulation, 2566 cases for hardware-in-the-loop (HIL) simulation and 497 cases for real flight. As it contains simulation data based on RflySim and real flight data, it is possible to improve the quantity while increasing the data quality. In each case, there are ULog, Telemetry log, Flight information and processed files for researchers to use and check. The RflyMAD dataset could be used as a benchmark for fault diagnosis methods and the support relationship between simulation data and real flight is verified through transfer learning methods. More methods as a baseline will be presented in the future, and RflyMAD will be updated with more data and types. In addition, the dataset and related toolkit can be accessed through https://rfly-openha.github.io/documents/4_resources/dataset.html.

The Segment Anything Model (SAM) has achieved a notable success in two-dimensional image segmentation in natural images. However, the substantial gap between medical and natural images hinders its direct application to medical image segmentation tasks. Particularly in 3D medical images, SAM struggles to learn contextual relationships between slices, limiting its practical applicability. Moreover, applying 2D SAM to 3D images requires prompting the entire volume, which is time- and label-consuming. To address these problems, we propose Slide-SAM, which treats a stack of three adjacent slices as a prediction window. It firstly takes three slices from a 3D volume and point- or bounding box prompts on the central slice as inputs to predict segmentation masks for all three slices. Subsequently, the masks of the top and bottom slices are then used to generate new prompts for adjacent slices. Finally, step-wise prediction can be achieved by sliding the prediction window forward or backward through the entire volume. Our model is trained on multiple public and private medical datasets and demonstrates its effectiveness through extensive 3D segmetnation experiments, with the help of minimal prompts. Code is available at \url{https://github.com/Curli-quan/Slide-SAM}.

This survey presents a comprehensive review of various methods and algorithms related to passing-through control of multi-robot systems in cluttered environments. Numerous studies have investigated this area, and we identify several avenues for enhancing existing methods. This survey describes some models of robots and commonly considered control objectives, followed by an in-depth analysis of four types of algorithms that can be employed for passing-through control: leader-follower formation control, multi-robot trajectory planning, control-based methods, and virtual tube planning and control. Furthermore, we conduct a comparative analysis of these techniques and provide some subjective and general evaluations., Comment: 18 pages, 19 figures

The planning and control of a robot swarm in a complex environment have attracted increasing attention. To this end, the idea of virtual tubes has been taken up in our previous work. Specifically, a virtual tube with varying widths has been planned to avoid collisions with obstacles in a complex environment. Based on the planned virtual tube for a large number of speed-constrained robots, the average forward speed and density along the virtual tube are further planned in this paper to ensure safety and improve efficiency. Compared with the existing methods, the proposed method is based on global information and can be applied to traversing narrow spaces for speed-constrained robot swarms. Numerical simulations and experiments are conducted to show that the safety and efficiency of the passing-through process are improved. A video about simulations and experiments is available on https://youtu.be/lJHdMQMqSpc.

It is often necessary for drones to complete delivery, photography, and rescue in the shortest time to increase efficiency. Many autonomous drone races provide platforms to pursue algorithms to finish races as quickly as possible for the above purpose. Unfortunately, existing methods often fail to keep training and racing time short in drone racing competitions. This motivates us to develop a high-efficient learning method by imitating the training experience of top racing drivers. Unlike traditional iterative learning control methods for accurate tracking, the proposed approach iteratively learns a trajectory online to finish the race as quickly as possible. Simulations and experiments using different models show that the proposed approach is model-free and is able to achieve the optimal result with low computation requirements. Furthermore, this approach surpasses some state-of-the-art methods in racing time on a benchmark drone racing platform. An experiment on a real quadcopter is also performed to demonstrate its effectiveness.

One-shot medical landmark detection gains much attention and achieves great success for its label-efficient training process. However, existing one-shot learning methods are highly specialized in a single domain and suffer domain preference heavily in the situation of multi-domain unlabeled data. Moreover, one-shot learning is not robust that it faces performance drop when annotating a sub-optimal image. To tackle these issues, we resort to developing a domain-adaptive one-shot landmark detection framework for handling multi-domain medical images, named Universal One-shot Detection (UOD). UOD consists of two stages and two corresponding universal models which are designed as combinations of domain-specific modules and domain-shared modules. In the first stage, a domain-adaptive convolution model is self-supervised learned to generate pseudo landmark labels. In the second stage, we design a domain-adaptive transformer to eliminate domain preference and build the global context for multi-domain data. Even though only one annotated sample from each domain is available for training, the domain-shared modules help UOD aggregate all one-shot samples to detect more robust and accurate landmarks. We investigated both qualitatively and quantitatively the proposed UOD on three widely-used public X-ray datasets in different anatomical domains (i.e., head, hand, chest) and obtained state-of-the-art performances in each domain. The code is available at https://github.com/heqin-zhu/UOD_universal_oneshot_detection., Comment: Eealy accepted by MICCAI 2023. 11pages, 4 figures, 2 tables. arXiv admin note: text overlap with arXiv:2203.06433

The augmentation parameters matter to few-shot semantic segmentation since they directly affect the training outcome by feeding the networks with varying perturbated samples. However, searching optimal augmentation parameters for few-shot segmentation models without annotations is a challenge that current methods fail to address. In this paper, we first propose a framework to determine the ``optimal'' parameters without human annotations by solving a distribution-matching problem between the intra-instance and intra-class similarity distribution, with the intra-instance similarity describing the similarity between the original sample of a particular anatomy and its augmented ones and the intra-class similarity representing the similarity between the selected sample and the others in the same class. Extensive experiments demonstrate the superiority of our optimized augmentation in boosting few-shot segmentation models. We greatly improve the top competing method by 1.27\% and 1.11\% on Abd-MRI and Abd-CT datasets, respectively, and even achieve a significant improvement for SSL-ALP on the left kidney by 3.39\% on the Abd-CT dataset.

With the high focus on autonomous aerial refueling recently, it becomes increasingly urgent to design efficient methods or algorithms to solve AAR problems in complicated aerial environments. Apart from the complex aerodynamic disturbance, another problem is the pose estimation error caused by the camera calibration error, installation error, or 3D object modeling error, which may not satisfy the highly accurate docking. The main objective of the effort described in this paper is the implementation of an image-based visual servo control method, which contains the establishment of an image-based visual servo model involving the receiver's dynamics and the design of the corresponding controller. Simulation results indicate that the proposed method can make the system dock successfully under complicated conditions and improve the robustness against pose estimation error.

This paper presents a novel method for efficiently solving a trajectory planning problem for swarm robotics in cluttered environments. Recent research has demonstrated high success rates in real-time local trajectory planning for swarm robotics in cluttered environments, but optimizing trajectories for each robot is still computationally expensive, with a computational complexity from $O\left(k\left(n_t,\varepsilon \right)n_t^2\right)$ to $ O\left(k\left(n_t,\varepsilon \right)n_t^3\right)$ where $n_t$ is the number of parameters in the parameterized trajectory, $\varepsilon$ is precision and $k\left(n_t,\varepsilon \right)$ is the number of iterations with respect to $n_t$ and $\varepsilon$. Furthermore, the swarm is difficult to move as a group. To address this issue, we define and then construct the optimal virtual tube, which includes infinite optimal trajectories. Under certain conditions, any optimal trajectory in the optimal virtual tube can be expressed as a convex combination of a finite number of optimal trajectories, with a computational complexity of $O\left(n_t\right)$. Afterward, a hierarchical approach including a planning method of the optimal virtual tube with minimizing energy and distributed model predictive control is proposed. In simulations and experiments, the proposed approach is validated and its effectiveness over other methods is demonstrated through comparison.

Airway segmentation, especially bronchioles segmentation, is an important but challenging task because distal bronchus are sparsely distributed and of a fine scale. Existing neural networks usually exploit sparse topology to learn the connectivity of bronchioles and inefficient shallow features to capture such high-frequency information, leading to the breakage or missed detection of individual thin branches. To address these problems, we contribute a new bronchial segmentation method based on Group Deep Dense Supervision (GDDS) that emphasizes fine-scale bronchioles segmentation in a simple-but-effective manner. First, Deep Dense Supervision (DDS) is proposed by constructing local dense topology skillfully and implementing dense topological learning on a specific shallow feature layer. GDDS further empowers the shallow features with better perception ability to detect bronchioles, even the ones that are not easily discernible to the naked eye. Extensive experiments on the BAS benchmark dataset have shown that our method promotes the network to have a high sensitivity in capturing fine-scale branches and outperforms state-of-the-art methods by a large margin (+12.8 % in BD and +8.8 % in TD) while only introducing a small number of extra parameters., Comment: Submitted to MICCAI2023

Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions. Researchers observe a significant performance disparity among subgroups with different demographic attributes, which is called model unfairness, and put lots of effort into carefully designing elegant architectures to address unfairness, which poses heavy training burden, brings poor generalization, and reveals the trade-off between model performance and fairness. To tackle these issues, we propose FairAdaBN by making batch normalization adaptive to sensitive attribute. This simple but effective design can be adopted to several classification backbones that are originally unaware of fairness. Additionally, we derive a novel loss function that restrains statistical parity between subgroups on mini-batches, encouraging the model to converge with considerable fairness. In order to evaluate the trade-off between model performance and fairness, we propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE., Comment: Accepted by MICCAI 2023

The improvement of the multi-mode capability of quantum memory can further improve the utilization efficiency of the quantum memory and reduce the requirement of quantum communication for storage units. In this letter, we experimentally investigate the multi-mode light multiplexing storage of orbital angular momentum (OAM) mode based on rubidium vapor, and demultiplexing by a photonic OAM mode splitter which combines a Sagnac loop with two dove prisms. Our results show a mode extinction ratio higher than 80$\%$ at 1 $\mu$s of storage time. Meanwhile, two OAM modes have been multiplexing stored and demultiplexed in our experimental configuration. We believe the experimental scheme may provide a possibility for high channel capacity and multi-mode quantum multiplexed quantum storage based on atomic ensembles.

Hybrid unmanned aerial vehicles (UAVs) integrate the efficient forward flight of fixed-wing and vertical takeoff and landing (VTOL) capabilities of multicopter UAVs. This paper presents the modeling, control and simulation of a new type of hybrid micro-small UAVs, coined as lifting-wing quadcopters. The airframe orientation of the lifting wing needs to tilt a specific angle often within $ 45$ degrees, neither nearly $ 90$ nor approximately $ 0$ degrees. Compared with some convertiplane and tail-sitter UAVs, the lifting-wing quadcopter has a highly reliable structure, robust wind resistance, low cruise speed and reliable transition flight, making it potential to work fully-autonomous outdoor or some confined airspace indoor. In the modeling part, forces and moments generated by both lifting wing and rotors are considered. Based on the established model, a unified controller for the full flight phase is designed. The controller has the capability of uniformly treating the hovering and forward flight, and enables a continuous transition between two modes, depending on the velocity command. What is more, by taking rotor thrust and aerodynamic force under consideration simultaneously, a control allocation based on optimization is utilized to realize cooperative control for energy saving. Finally, comprehensive Hardware-In-the-Loop (HIL) simulations are performed to verify the advantages of the designed aircraft and the proposed controller.

In this paper, we propose an effective unified control law for accurately tracking agile trajectories for lifting-wing quadcopters with different installation angles, which have the capability of vertical takeoff and landing (VTOL) as well as high-speed cruise flight. First, we derive a differential flatness transform for the lifting-wing dynamics with a nonlinear model under coordinated turn condition. To increase the tracking performance on agile trajectories, the proposed controller incorporates the state and input variables calculated from differential flatness as feedforward. In particular, the jerk, the 3-order derivative of the trajectory, is converted into angular velocity as a feedforward item, which significantly improves the system bandwidth. At the same time, feedback and feedforward outputs are combined to deal with external disturbances and model mismatch. The control algorithm has been thoroughly evaluated in the outdoor flight tests, which show that it can achieve accurate trajectory tracking.

In our previous work, we design a trapezoid virtual tube to guide robotic swarms through narrow openings. This paper extends the application of the trapezoid virtual tube to the situations where there are static obstacles inside and robots have strict speed constraints. We first propose a distributed swarm controller for the trapezoid virtual tube without obstacles and present the relationship between the trapezoid virtual tube and speed constraints. Then a switching logic for obstacle avoidance is proposed by dividing the trapezoid virtual tube containing static obstacles into several sub trapezoid virtual tubes without obstacles. Formal analyses and proofs are presented to demonstrate that all robots can pass through the trapezoid virtual tube safely. Besides, we validate the effectiveness of our method through numerical simulations and real experiments., Comment: 12 pages, 13 figures

This study proposes a uniform passive fault-tolerant control (FTC) method for a quadcopter that does not rely on fault information subject to one, two adjacent, two opposite, or three rotors failure. The uniform control implies that the passive FTC is able to cover the condition from quadcopter fault-free to rotor failure without controller switching. To achieve the purpose of the passive FTC, the rotors' fault is modeled as a disturbance acting on the virtual control of the quadcopter system. The disturbance estimate is used directly for the passive FTC with rotor failure. To avoid controller switching between normal control and FTC, a dynamic control allocation is used. In addition, the closed-loop stability has been analyzed and a virtual control feedback is adopted to achieve the passive FTC for the quadcopter with two and three rotor failure. To validate the proposed uniform passive FTC method, outdoor experiments are performed for the first time, which have demonstrated that the hovering quadcopter is able to recover from one rotor failure by the proposed controller and continue to fly even if two adjacent, two opposite, or three rotors fail, without any rotor fault information and controller switching., Comment: We found some important errors in the paper that need to be corrected

Contrastive learning (CL) is a form of self-supervised learning and has been widely used for various tasks. Different from widely studied instance-level contrastive learning, pixel-wise contrastive learning mainly helps with pixel-wise tasks such as medical landmark detection. The counterpart to an instance in instance-level CL is a pixel, along with its neighboring context, in pixel-wise CL. Aiming to build better feature representation, there is a vast literature about designing instance augmentation strategies for instance-level CL; but there is little similar work on pixel augmentation for pixel-wise CL with a pixel granularity. In this paper, we attempt to bridge this gap. We first classify a pixel into three categories, namely low-, medium-, and high-informative, based on the information quantity the pixel contains. Inspired by the ``InfoMin" principle, we then design separate augmentation strategies for each category in terms of augmentation intensity and sampling ratio. Extensive experiments validate that our information-guided pixel augmentation strategy succeeds in encoding more discriminative representations and surpassing other competitive approaches in unsupervised local feature matching. Furthermore, our pretrained model improves the performance of both one-shot and fully supervised models. To the best of our knowledge, we are the first to propose a pixel augmentation method with a pixel granularity for enhancing unsupervised pixel-wise contrastive learning.

Searching in a denied environment is challenging for swarm robots as no assistance from GNSS, mapping, data sharing, and central processing is allowed. However, using olfactory and auditory signals to cooperate like animals could be an important way to improve the collaboration of swarm robots. In this paper, an Olfactory-Auditory augmented Bug algorithm (OA-Bug) is proposed for a swarm of autonomous robots to explore a denied environment. A simulation environment is built to measure the performance of OA-Bug. The coverage of the search task can reach 96.93% using OA-Bug, which is significantly improved compared with a similar algorithm, SGBA. Furthermore, experiments are conducted on real swarm robots to prove the validity of OA-Bug. Results show that OA-Bug can improve the performance of swarm robots in a denied environment., Comment: 7 pages, 6 figures, accepted by 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

In order to guide the multi-agent system in a cluttered environment, a connected quadrangle virtual tube is designed for all agents to keep moving within it, whose basis is called the single trapezoid virtual tube. There is no obstacle inside the tube, namely the area inside the tube can be seen as a safety zone. Then, a distributed swarm controller is proposed for the single trapezoid virtual tube passing problem. This issue is resolved by a gradient vector field method with no local minima. Formal analyses and proofs are made to show that all agents are able to pass the single trapezoid virtual tube. Finally, a modified controller is put forward for convenience in practical use. For the connected quadrangle virtual tube, a modified switching logic is proposed to avoid the deadlock and prevent agents from moving outside the virtual tube. Finally, the effectiveness of the proposed method is validated by numerical simulations and real experiments., Comment: 12 pages,14 figures. arXiv admin note: substantial text overlap with arXiv:2112.01006

Learning-based control policies are widely used in various tasks in the field of robotics and control. However, formal (Lyapunov) stability guarantees for learning-based controllers with nonlinear dynamical systems are difficult to obtain. We propose a novel control approach, namely Control with Patterns (CWP), to address the stability issue over data sets corresponding to nonlinear dynamical systems. For such data sets, we introduce a new definition, namely exponential attraction on data sets, to describe the nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is transformed into a problem of pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method to perform CWP without knowledge of the system dynamics. Finally, the effectiveness of CWP based on D-learning is demonstrated through simulations and real flight experiments. In these experiments, the position of the multicopter is stabilized using real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem., Comment: Accepted for publication at 8th Conference on Robot Learning (CoRL), Munich, Germany. 2024

Safety is always the priority in aviation. However, current state-of-the-art passive fault-tolerant control is too conservative to use; current state-of-the-art active fault-tolerant control requires time to perform fault detection and diagnosis, and control switching. But it may be later to recover impaired aircraft. Most designs depend on failures determined as a priori and cannot deal with fault, causing the original system's state to be uncontrollable. However, experienced human pilots can save a serve impaired aircraft as far as they can. Motivated by this, this paper develops a principle to try to explain human pilot behavior behind, coined the gravity-compensation-first principle. This further supports reliable flight control for aircraft such as quadcopters and tail-sitter unmanned aerial vehicles.

To guide the movement of a robotic swarm in a corridor-like environment, a curve virtual tube with no obstacle inside is designed in our previous work. This paper generalizes the controller design to the condition that all robots have self-localization drifts and precise relative navigation, where the flocking algorithm is introduced to reduce the negative impact of the self-localization drift. It is shown that the cohesion behavior and the velocity alignment behavior are able to reduce the influence of the position measurement drift and the velocity measurement error, respectively. For the convenience in practical use, a modified vector field controller with five control terms is put forward. Finally, the effectiveness of the proposed method is validated by numerical simulations and real experiments., Comment: 8 pages, 10 figures

While medical images such as computed tomography (CT) are stored in DICOM format in hospital PACS, it is still quite routine in many countries to print a film as a transferable medium for the purposes of self-storage and secondary consultation. Also, with the ubiquitousness of mobile phone cameras, it is quite common to take pictures of CT films, which unfortunately suffer from geometric deformation and illumination variation. In this work, we study the problem of recovering a CT film, which marks \textbf{the first attempt} in the literature, to the best of our knowledge. We start with building a large-scale head CT film database CTFilm20K, consisting of approximately 20,000 pictures, using the widely used computer graphics software Blender. We also record all accompanying information related to the geometric deformation (such as 3D coordinate, depth, normal, and UV maps) and illumination variation (such as albedo map). Then we propose a deep framework called \textbf{F}ilm \textbf{I}mage \textbf{Re}covery \textbf{Net}work (\textbf{FIReNet}) to tackle geometric deformation and illumination variation using the multiple maps extracted from the CT films to collaboratively guide the recovery process. Finally, we convert the dewarped images to DICOM files with our cascade model for further analysis such as radiomics feature extraction. Extensive experiments demonstrate the superiority of our approach over the previous approaches. We plan to open source the simulated images and deep models for promoting the research on CT film image analysis.

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing self-supervised methods applied in natural imaging tasks focus on designing proxy tasks for unlabeled data. For example, contrastive learning is often based on the fact that an image and its transformed version share the same identity. However, pixel annotations contain much valuable information for medical image segmentation, which is largely ignored in contrastive learning. In this work, we propose a novel pre-training framework called Mixed Contrastive Learning (MixCL) that leverages both image identities and pixel labels for better modeling by maintaining identity consistency, label consistency, and reconstruction consistency together. Consequently, thus pre-trained model has more robust representations that characterize medical images. Extensive experiments demonstrate the effectiveness of the proposed method, improving the baseline by 5.28% and 14.12% in Dice coefficient when 5% labeled data of Spleen and 15% of BTVC are used in fine-tuning, respectively.

In the paper, we present an approach for learning a single model that universally segments 33 anatomical structures, including vertebrae, pelvic bones, and abdominal organs. Our model building has to address the following challenges. Firstly, while it is ideal to learn such a model from a large-scale, fully-annotated dataset, it is practically hard to curate such a dataset. Thus, we resort to learn from a union of multiple datasets, with each dataset containing the images that are partially labeled. Secondly, along the line of partial labelling, we contribute an open-source, large-scale vertebra segmentation dataset for the benefit of spine analysis community, CTSpine1K, boasting over 1,000 3D volumes and over 11K annotated vertebrae. Thirdly, in a 3D medical image segmentation task, due to the limitation of GPU memory, we always train a model using cropped patches as inputs instead a whole 3D volume, which limits the amount of contextual information to be learned. To this, we propose a cross-patch transformer module to fuse more information in adjacent patches, which enlarges the aggregated receptive field for improved segmentation performance. This is especially important for segmenting, say, the elongated spine. Based on 7 partially labeled datasets that collectively contain about 2,800 3D volumes, we successfully learn such a universal model. Finally, we evaluate the universal model on multiple open-source datasets, proving that our model has a good generalization performance and can potentially serve as a solid foundation for downstream tasks.

Contrastive learning based methods such as cascade comparing to detect (CC2D) have shown great potential for one-shot medical landmark detection. However, the important cue of relative distance between landmarks is ignored in CC2D. In this paper, we upgrade CC2D to version II by incorporating a simple-yet-effective relative distance bias in the training stage, which is theoretically proved to encourage the encoder to project the relatively distant landmarks to the embeddings with low similarities. As consequence, CC2Dv2 is less possible to detect a wrong point far from the correct landmark. Furthermore, we present an open-source, landmark-labeled dataset for the measurement of biomechanical parameters of the lower extremity to alleviate the burden of orthopedic surgeons. The effectiveness of CC2Dv2 is evaluated on the public dataset from the ISBI 2015 Grand-Challenge of cephalometric radiographs and our new dataset, which greatly outperforms the state-of-the-art one-shot landmark detection approaches.